Processing 2,500 lines of code (~24,500 tokens) with Codestral 2501 costs $0.00735 for codebase ingestion and $0.0118 for an AI-powered code review and refactoring pass.
Quick answer
A 2,500 lines of code codebase is estimated at 24,500 tokens for Codestral 2501. Ingestion costs $0.00735; a review and refactoring pass with roughly 20% output costs about $0.0118.
Method & trust
Code is estimated at a tokenizer-specific tokens-per-line ratio, then priced separately for repository context and generated review output. Comments, minified files, tests, and repeated context can materially change the bill.
Feed 2,500 lines of code into the prompt context for repository search, Q&A, or architecture planning.
Ingest 2,500 lines of code and generate audit findings, unit test recommendations, and refactor diffs.
Codestral 2501 writes 2,500 lines of code from scratch based on product specifications.
| Model | Provider | Code Ingestion | Cached Ingestion | Code Review Cost | Context Limit |
|---|---|---|---|---|---|
| Codestral 2501 (Current) | mistral | $0.00735 | $0.000735 | $0.0118 | 256,000 |
| GPT-5.3 Codex | openai | $0.0446 | $0.004462 | $0.116 | 256,000 |
| DeepSeek Coder V2.5 | deepseek | $0.00392 | $0.000392 | $0.005488 | 128,000 |
| Grok Build 0.1 | xai | $0.028 | $0.0056 | $0.0392 | 256,000 |
| Qwen 2.5 Coder 32B | qwen | $0.0056 | $0.00056 | $0.00896 | 128,000 |
| GLM-5.3 (Z.ai) | zai | $0.0392 | $0.00728 | $0.0638 | 1,048,576 |
On average, code yields approximately 9.8 tokens per line in Codestral 2501 (mistral_bpe tokenizer). Indentation, brackets, camelCase variable names, and comments slightly increase token density compared to plain English text. 2,500 lines of code produces approximately 24,500 tokens.
Sending 2,500 lines of code as context and generating a thorough code review with recommendations costs approximately $0.0118. Utilizing prompt caching on repeat turns or static repository definitions drops this to $0.005145.
Codestral 2501 has a context window of 256,000 tokens. 2,500 lines of code consumes 9.57% of its total available context.